Update app.py

app.py

@@ -56,7 +56,7 @@ if not torch.cuda.is_available():
 if torch.cuda.is_available():
 
     # Model and Tokenizer Configuration
-    model_id = "meta-llama/Llama-2-7b-chat-hf"
+    model_id = "meta-llama/Llama-3.1-8B-Instruct"
     bnb_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_use_double_quant=False,